Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dollar amounts or prices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.56
    ren
    0.53
    wissenschaft
    0.51
    il
    0.50
     vom
    0.48
    setVisible
    0.48
    ir
    0.48
     درباره
    0.46
    зываем
    0.46
    polling
    0.45
    POSITIVE LOGITS
     slopes
    0.51
     optimum
    0.48
     ہوگئی
    0.48
    适
    0.48
     limiting
    0.46
     soluzioni
    0.46
    ก
    0.46
     hopes
    0.46
    0.46
    ácil
    0.46
    Act Density 0.000%

    No Known Activations